Blaine is a computer scientist currently working on AI safety in Japan. He explains how Chat-GPT works, and makes a case for thinking about AI safety, be that through technical alignment, interpretability research, or developing good policies for AI governance. Blaine is a computer scientist from England and the founder of [ Ссылка ]. His research backgrounds are formal verification, Bayesian statistics and computer vision. This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at [ Ссылка ]

свернуть